Re: Death by pointers.

In article 95-09-120,
John Carter <ECE@dwaf-hri.pwv.gov.za> wrote:
] >to ensure better use of cache lines, but in C, it cannot be, because
] >some_array_ptr MIGHT be aliased to global. For large enough values of
] >m, the transformed piece of code is at least 3 times faster on a
] >high-performance workstation. Fortran rules usually allow this
] >transformation.
[...]
] Parallel programming can be really hairy if you go at it at fine time
] grain, but there is more than enough going on on a modern workstation
] to merely paralell process at a very high level.


Now tell us all how you want to recode the above-mentionned loop so as to
compensate the factor of 3 speed decrease by a factor of (at least) 3
parallelism. (since this is probably the inner loop, it probably eats up around
80% of the program's time. Don't bother parallelise the rest before you
parallelise the loop).




Stefan
--

Return to the comp.compilers page.
Search the comp.compilers archives again.